AI Paper Atlas

Research map / Detection and segmentation / CNN features

Object Detection Networks on Convolutional Feature Maps

Shaoqing Ren, Kaiming He, Ross Girshick, Xiangyu Zhang, Jian Zhong Sun

TPAMI 2016 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 470 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace SVM on RoI features with a 4fc MLP NoC (ablation)NoC on ZF · PASCAL VOC 07 testmAP (%): 45.8 -> 53.6Improved
increase MLP NoC depth from 2 fc to 4 fc layers (ablation)NoC on ZF · PASCAL VOC 07 testmAP (%): 49.0 -> 53.1 -> 53.6Improved
add 2 conv layers to the 3fc NoC (07+12 training) (ablation)NoC on ZF · PASCAL VOC 07 testmAP (%): 56.5 -> 58.9Improved
add 2 conv layers to the 3fc NoC (07 trainval only) (ablation)NoC on ZF · PASCAL VOC 07 testmAP (%): 53.1 -> 51.4Hurt
add 3rd conv layer beyond 2 conv (ablation)NoC on ZF · PASCAL VOC 07 test (07+12)mAP (%): 58.9 -> 58.8No clear effect
add maxout for scale selection after conv+1 (ablation)2conv3fc NoC on ZF · PASCAL VOC 07 test (07+12)mAP (%): 58.9 -> 60.7Improved
use pre-trained fc init instead of random init (3fc NoC, 07+12) (ablation)NoC on ZF · PASCAL VOC 07 testmAP (%): 56.5 -> 58.0Improved
fine-tune maxout 2conv3fc NoC from pre-trained instead of random init (ablation)NoC on ZF · PASCAL VOC 07 test (07+12)mAP (%): 60.7 -> 62.9Improved
use deeper shared features (VGG-16 to VGG-19) (ablation)3fc NoC · PASCAL VOC 07 testmAP (%): 64.6 -> 65.1Improved
increase classifier depth (3fc to 2conv3fc) on VGG-16 features (ablation)NoC · PASCAL VOC 07 testmAP (%): 64.6 -> 66.1Improved
add maxout 2conv3fc NoC to reduce localization error (ablation)NoC · PASCAL VOC 07 (error analysis)localization error (%): 28.1 -> 22.6 (ZF), 24.8 -> 20.1 (VGG-16)Improved
add 3fc MLP NoC to naive Faster R-CNN (ablation)Faster R-CNN ResNet-101 · MS COCO valAP (%): 21.3 -> 26.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy